Kadir Nar
Kadir Nar
You don't need to wait for the training code of the Llama-Omni model. You can use different Omni models. Llama-Omni is not a very good model. https://github.com/VITA-MLLM/VITA?tab=readme-ov-file#-training
> > You don't need to wait for the training code of the Llama-Omni model. You can use different Omni models. Llama-Omni is not a very good model. > >...
@AMohamedAakhil , Can you give information about the json file? Can you share a sample json file? How should I prepare a dataset?
Thank you for the development. Have you tested it?
Link is broken. Can you link again?
I'll take care of it on the weekend.
I'm really busy. You can solve this by fixing this part of the code. https://github.com/kadirnar/ComfyUI-YOLO/blob/main/nodes.py#L539 Is the model you're using .pt extension?
> Here is the fix: [#14](https://github.com/kadirnar/ComfyUI-YOLO/pull/14) Thanks for your contribution.
> [#14](https://github.com/kadirnar/ComfyUI-YOLO/pull/14) didn't fix this bug. It makes it worse. It creates a folder like `ComfyUI/ComfyUI/models/ultralytics`. Please fix it by using `import folder_paths` and `os.path.join(folder_paths.models_dir, 'ultralytics')` to get the path....